agentleFS
TheGoat395TheGoat395/Codex-Skills/skills/premium-web-build-gate/SKILL.md

premium-web-build-gate

Skill136 starsChanged 5 months agoMITView on GitHub

Check premium specs before implementation.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check that a new premium build or substantial redesign has enough agreed direction to implement reliably.

    line 8
  2. Distinctive:

    Read the build-ready specification guide for the relevant content, visual, motion, tooling and QA criteria when a new build or substantial …

    line 19
  3. Distinctive:

    Use the shared quality tiers when the delivery depth is unclear.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Premium Web Build Gate

Check that a new premium build or substantial redesign has enough agreed direction to implement reliably. Fill the actual decision gaps while preserving the requested quality tier, real content, accessibility, responsive behavior and verification requirements.

Scope first

  • Reuse an adequate existing brief, blueprint, design system and approved stack. Do not recreate them because this skill was selected.
  • For a localized change, check only the affected requirements and proceed to its implementation owner. A typo or component fix does not require a whole-site spec or reference-research project.
  • For a review-only request, return findings or a proposed spec and remain read-only.
  • Continue routine reversible work within existing authorization. Ask only for a consequential unresolved choice that cannot be inferred or handled with a reasonable reversible assumption. Preserve real release and client-approval boundaries.

Resolve missing decisions

Read the build-ready specification guide for the relevant content, visual, motion, tooling and QA criteria when a new build or substantial redesign has unresolved decisions. Use only the applicable fields; no fixed number of references, new document or additional skill installation is required.

Use the shared quality tiers when the delivery depth is unclear. An installed route-sellable-web-tier specialist is optional; the bundled reference is sufficient when it is absent.

Complete and verify

Once direction is adequate, continue the requested implementation through running, inspecting, correcting and validating affected behavior. Preserve source truth, the selected stack and supported accessibility/reduced-motion behavior. Existing project release gates remain applicable.

For an audit, report the specific gaps and their evidence. For implementation, report changed files and checks actually performed. A completed spec alone is not a completed website, and unperformed browser or production checks remain unverified.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.